Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Filter by category
55,055 results · page 681 of 1,836
- View details
skills-evalSkillAI & models
Lets your agent audit and score the quality of your agent skills and suggest improvements.
Ready to connect★ 335
- View details
smart-sourcingSkillProductivity
Lets your agent pick the best research sources, balancing accuracy against token cost before a task.
Ready to connect★ 335
- View details
Speckit ClarifySkillAI & models
Lets your agent ask targeted questions to clear up ambiguities in a spec before building.
★ 335
- View details
Speckit TasksSkillMedia
Lets your agent turn design documents into a task list ordered by dependencies.
★ 335
- View details
Speckit TaskstoissuesSkillProductivity
Lets your agent turn task list entries in tasks.md into GitHub Issues.
★ 335
- View details
stewardshipSkillAI & models
Guides your agent to apply stewardship virtues like care and diligence when writing or reviewing plugin code.
Ready to connect★ 335
- View details
Stewardship HealthSkillAI & models
Lets your agent view stewardship health metrics for one plugin or all plugins.
★ 335
- View details
storage-templatesSkillFiles & storage
Gives your agent reusable templates, naming conventions, and maturity stages for organizing notes and documents.
Ready to connect★ 335
- View details
Structured ReviewSkillMonitoring & ops
Lets your agent run a structured review that logs evidence and formats the findings.
★ 335
- View details
subagent-testingSkillAI & models
Lets your agent test other skills using TDD in fresh subagent sessions to get unbiased results.
Ready to connect★ 335
- View details
summonSkillAI & models
Lets your agent run a backlog of work items through a full development pipeline automatically, step by step.
Ready to connect★ 335
- View details
supply-chain-advisorySkillMonitoring & ops
Lets your agent audit project dependencies for bad versions, lockfile drift, and artifact integrity issues.
Ready to connect★ 335
- View details
testing-quality-standardsSkillMonitoring & ops
Gives your agent testing quality standards, coverage thresholds, and checklists to set test gates and review a test suite.
Ready to connect★ 335
- View details
token-conservationSkillAI & models
Keeps your agent's token use under control by setting read budgets, compressing context, and warning when quota runs low.
Ready to connect★ 335
- View details
UnbloatSkillFiles & storage
Lets your agent clean up dead code, duplicate files, and unused dependencies, with approval and backups before deleting.
★ 335
- View details
Uninstall WatchdogSkillFiles & storage
Lets your agent remove the watchdog daemon and clean up its leftover files.
★ 335
- View details
uninstall-watchdogSkillFiles & storage
Lets your agent remove the watchdog daemon and its files to stop automated session relaunching.
Ready to connect★ 335
- View details
Update All PluginsSkillAI & models
Lets your agent update all installed Claude Code plugins from every marketplace at once.
★ 335
- View details
Update DependenciesSkillAI & models
Lets your agent scan project dependencies and update them across ecosystems while detecting version conflicts.
★ 335
- View details
Update LabelsSkillAI & models
Lets your agent reorganize GitHub issue labels into type, priority, and effort groups.
★ 335
- View details
Update TestsSkillAI & models
Lets your agent generate and update tests for changed code using TDD/BDD with quality checks.
★ 335
- View details
Update TutorialSkillWeb & browsing
Lets your agent create or update tutorials with recorded terminal and browser sessions.
★ 335
- View details
Upgrade ProjectSkillAI & models
Lets your agent update existing project configurations to current best practices with selective component upgrades.
★ 335
- View details
usage-loggingSkillDatabases & data
Lets your agent log operation costs, tokens, and sessions to structured JSONL files for audits and usage analytics.
Ready to connect★ 335
- View details
utilitySkillAI & models
Scores your agent's planned actions by expected gain, cost, uncertainty, and redundancy before dispatch.
Ready to connect★ 335
- View details
Validate HookSkillSecurity
Checks your agent's hooks for security issues, performance problems, and SDK rule violations.
★ 335
- View details
Validate PluginSkillAI & models
Checks that a plugin's structure, schema, and naming are correct.
★ 335
- View details
Validate PrSkillAI & models
Lets your agent check a pull request by generating and running a test plan from its code changes.
★ 335
- View details
Verify PluginSkillAI & models
Lets your agent check a plugin's verified history using GitHub attestations.
★ 335
- View details
Voice ExtractSkillAI & models
Lets your agent analyze writing samples and build a reusable profile of your writing voice.
★ 335
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
54,624 of the 55,055 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.